{"id":"https://openalex.org/W2019324975","doi":"https://doi.org/10.1142/s0219720010005051","title":"SHORT PROKARYOTIC DNA FRAGMENT BINNING USING A HIERARCHICAL CLASSIFIER BASED ON LINEAR DISCRIMINANT ANALYSIS AND PRINCIPAL COMPONENT ANALYSIS","display_name":"SHORT PROKARYOTIC DNA FRAGMENT BINNING USING A HIERARCHICAL CLASSIFIER BASED ON LINEAR DISCRIMINANT ANALYSIS AND PRINCIPAL COMPONENT ANALYSIS","publication_year":2010,"publication_date":"2010-08-23","ids":{"openalex":"https://openalex.org/W2019324975","doi":"https://doi.org/10.1142/s0219720010005051","mag":"2019324975","pmid":"https://pubmed.ncbi.nlm.nih.gov/21121023"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720010005051","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720010005051","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102007688","display_name":"Hao Zheng","orcid":"https://orcid.org/0009-0000-6483-8433"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HAO ZHENG","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, 210 Technology Circle, Savannah, GA 31407, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, 210 Technology Circle, Savannah, GA 31407, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108819118","display_name":"Hongwei Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HONGWEI WU","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, 210 Technology Circle, Savannah, GA 31407, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, 210 Technology Circle, Savannah, GA 31407, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.4978,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.81007907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"08","issue":"06","first_page":"995","last_page":"1011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10141","display_name":"Probiotics and Fermented Foods","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.8269227743148804},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.7368289232254028},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6777302622795105},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6206842660903931},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.596159040927887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.562229335308075},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4783320426940918},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4727255702018738},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4716341197490692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4385005831718445},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.32608532905578613},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3248381018638611},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.20560306310653687},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.10455799102783203}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8269227743148804},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.7368289232254028},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6777302622795105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6206842660903931},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.596159040927887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.562229335308075},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4783320426940918},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4727255702018738},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4716341197490692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4385005831718445},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.32608532905578613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3248381018638611},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.20560306310653687},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10455799102783203}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005827","descriptor_name":"Genetics, Microbial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005827","descriptor_name":"Genetics, Microbial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005827","descriptor_name":"Genetics, Microbial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016002","descriptor_name":"Discriminant Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016002","descriptor_name":"Discriminant Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016002","descriptor_name":"Discriminant Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D022761","descriptor_name":"Gene Transfer, Horizontal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D022761","descriptor_name":"Gene Transfer, Horizontal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D022761","descriptor_name":"Gene Transfer, Horizontal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720010005051","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720010005051","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:21121023","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21121023","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of bioinformatics and computational biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W298701694","https://openalex.org/W1539550196","https://openalex.org/W1560556066","https://openalex.org/W1562379206","https://openalex.org/W2018567038","https://openalex.org/W2020449264","https://openalex.org/W2021380741","https://openalex.org/W2029437806","https://openalex.org/W2043602518","https://openalex.org/W2076115496","https://openalex.org/W2081676964","https://openalex.org/W2090237271","https://openalex.org/W2091564674","https://openalex.org/W2098290178","https://openalex.org/W2099151387","https://openalex.org/W2112840243","https://openalex.org/W2113601822","https://openalex.org/W2116895571","https://openalex.org/W2124637227","https://openalex.org/W2131227009","https://openalex.org/W2132415967","https://openalex.org/W2150337627","https://openalex.org/W2153990926","https://openalex.org/W2163352587","https://openalex.org/W2163614729","https://openalex.org/W2165870892","https://openalex.org/W2170798597","https://openalex.org/W2171777099","https://openalex.org/W4205687621"],"related_works":["https://openalex.org/W2052589448","https://openalex.org/W2765337000","https://openalex.org/W3104072235","https://openalex.org/W2391447249","https://openalex.org/W2312955079","https://openalex.org/W2350996391","https://openalex.org/W2066119650","https://openalex.org/W2059615944","https://openalex.org/W4224057882","https://openalex.org/W1993173579"],"abstract_inverted_index":{"Metagenomics":[0],"is":[1,12,34,46],"an":[2,15,49],"emerging":[3],"field":[4],"in":[5],"which":[6],"the":[7,20,38,73,97,101,119,136,142,149,157,160,172,181,187],"power":[8],"of":[9,30,100,108,111,135,141,148,159,186],"genomic":[10],"analysis":[11,92],"applied":[13],"to":[14,22,53,95],"entire":[16],"microbial":[17,27],"community,":[18],"bypassing":[19],"need":[21],"isolate":[23],"and":[24,57,75,147,197,203],"culture":[25],"individual":[26],"species.":[28],"Assembling":[29],"metagenomic":[31,87],"DNA":[32,131],"fragments":[33,132],"very":[35],"much":[36],"like":[37],"overlap-layout-consensus":[39],"procedure":[40],"for":[41,81,128],"assembling":[42],"isolated":[43],"genomes,":[44],"but":[45],"augmented":[47],"by":[48,162],"additional":[50],"binning":[51,82,129,200],"step":[52],"differentiate":[54],"scaffolds,":[55],"contigs":[56],"unassembled":[58],"reads":[59],"into":[60,133,139,145,152],"various":[61],"taxonomic":[62],"groups.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"employed":[68],"n-mer":[69],"oligonucleotide":[70],"frequencies":[71],"as":[72,169,171],"features":[74],"developed":[76],"a":[77,194],"hierarchical":[78,105],"classifier":[79,106],"(PCAHIER)":[80],"short":[83],"(\u2264":[84],"1,000":[85],"bps)":[86],"fragments.":[88],"The":[89,104,184],"principal":[90],"component":[91],"was":[93,189],"used":[94,174],"reduce":[96],"high":[98],"dimensionality":[99],"feature":[102],"space.":[103],"consists":[107],"four":[109],"layers":[110],"local":[112,124],"classifiers":[113,125],"that":[114],"are":[115,126],"implemented":[116],"based":[117],"on":[118],"linear":[120],"discriminant":[121],"analysis.":[122],"These":[123],"responsible":[127],"prokaryotic":[130],"superkingdoms,":[134],"same":[137,143,150],"superkingdom":[138],"phyla,":[140],"phylum":[144],"genera,":[146],"genus":[151],"species,":[153],"respectively.":[154],"We":[155],"evaluated":[156],"performance":[158],"PCAHIER":[161,188],"using":[163],"our":[164],"own":[165],"simulated":[166],"data":[167,178],"sets":[168],"well":[170],"widely":[173],"simHC":[175],"synthetic":[176],"metagenome":[177],"set":[179],"from":[180],"IMG/M":[182],"system.":[183],"effectiveness":[185],"demonstrated":[190],"through":[191],"comparisons":[192],"against":[193],"non-hierarchical":[195],"classifier,":[196],"two":[198],"existing":[199],"algorithms":[201],"(TETRA":[202],"Phylopythia).":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}